Chapter 5 Bacteria

genome_metadata %>% 
  filter(domain == "d__Bacteria") %>% 
  group_by(phylum) %>%
  summarise(mag_n=n()) %>%
  arrange(-mag_n) %>%
  tt()
tinytable_pvwa2q2q6tldh3gob0d1
phylum mag_n
p__Bacteroidota 369
p__Bacillota_A 251
p__Pseudomonadota 157
p__Bacillota 54
p__Desulfobacterota 37
p__Verrucomicrobiota 29
p__Patescibacteria 27
p__Cyanobacteriota 23
p__Fusobacteriota 12
p__Chloroflexota 10
p__Bacillota_C 9
p__Deferribacterota 8
p__Acidobacteriota 6
p__Bacillota_B 5
p__Desulfobacterota_F 5
p__Actinomycetota 4
p__Planctomycetota 4
p__Spirochaetota 4
p__Campylobacterota 3
p__Myxococcota 2
p__ 1
p__Chlamydiota 1
p__Desulfobacterota_G 1
p__Fibrobacterota 1
p__J088 1
p__JAKLEM01 1
p__Omnitrophota 1

5.1 Genome quality

genome_metadata %>% 
    summarise(completeness_mean=mean(completeness) %>% round(2) %>% as.character(), 
              completeness_sd=sd(completeness) %>% round(2) %>% as.character(), 
              contamination_mean=mean(contamination) %>% round(2), 
              contamination_sd=sd(contamination) %>% round(2)) %>%
    unite("Completeness",completeness_mean, completeness_sd, sep = " ± ", remove = TRUE) %>%
    unite("Contamination",contamination_mean, contamination_sd, sep = " ± ", remove = TRUE) %>%
    tt()
tinytable_pgxhjh0q91rhuge3usrz
Completeness Contamination
82.78 ± 17.27 1.9 ± 2.36
#Generate quality biplot
genome_biplot <- genome_metadata %>%
  select(c(genome,domain,phylum,completeness,contamination,length)) %>%
  arrange(match(genome, rev(genome_tree$tip.label))) %>% #sort MAGs according to phylogenetic tree
  ggplot(aes(x=completeness,y=contamination,size=length,color=phylum)) +
              geom_point(alpha=0.7) +
                    ylim(c(10,0)) +
                    scale_color_manual(values=phylum_colors) +
                    labs(y= "Contamination", x = "Completeness") +
                    theme_classic() +
                    theme(legend.position = "none")

#Generate contamination boxplot
genome_contamination <- genome_metadata %>%
            ggplot(aes(y=contamination)) +
                    ylim(c(10,0)) +
                    geom_boxplot(colour = "#999999", fill="#cccccc") +
                    theme_void() +
                    theme(legend.position = "none",
                        axis.title.x = element_blank(),
                        axis.title.y = element_blank(),
                        axis.text.y=element_blank(),
                        axis.ticks.y=element_blank(),
                        axis.text.x=element_blank(),
                        axis.ticks.x=element_blank(),
                        plot.margin = unit(c(0, 0, 0.40, 0),"inches")) #add bottom-margin (top, right, bottom, left)

#Generate completeness boxplot
genome_completeness <- genome_metadata %>%
        ggplot(aes(x=completeness)) +
                xlim(c(50,100)) +
                geom_boxplot(colour = "#999999", fill="#cccccc") +
                theme_void() +
                theme(legend.position = "none",
                    axis.title.x = element_blank(),
                    axis.title.y = element_blank(),
                    axis.text.y=element_blank(),
                    axis.ticks.y=element_blank(),
                    axis.text.x=element_blank(),
                    axis.ticks.x=element_blank(),
                    plot.margin = unit(c(0, 0, 0, 0.50),"inches")) #add left-margin (top, right, bottom, left)

#Render composite figure
grid.arrange(grobs = list(genome_completeness,genome_biplot,genome_contamination),
        layout_matrix = rbind(c(1,1,1,1,1,1,1,1,1,1,1,4),
                              c(2,2,2,2,2,2,2,2,2,2,2,3),
                              c(2,2,2,2,2,2,2,2,2,2,2,3),
                              c(2,2,2,2,2,2,2,2,2,2,2,3),
                              c(2,2,2,2,2,2,2,2,2,2,2,3),
                              c(2,2,2,2,2,2,2,2,2,2,2,3),
                              c(2,2,2,2,2,2,2,2,2,2,2,3),
                              c(2,2,2,2,2,2,2,2,2,2,2,3),
                              c(2,2,2,2,2,2,2,2,2,2,2,3),
                              c(2,2,2,2,2,2,2,2,2,2,2,3),
                              c(2,2,2,2,2,2,2,2,2,2,2,3),
                              c(2,2,2,2,2,2,2,2,2,2,2,3)))

5.2 Functional overview

# Aggregate basal GIFT into elements
function_table <- genome_gifts %>%
    to.elements(., GIFT_db)

# Generate  basal tree
function_tree <- force.ultrametric(genome_tree, method="extend") %>%
                ggtree(., size = 0.3) 
***************************************************************
*                          Note:                              *
*    force.ultrametric does not include a formal method to    *
*    ultrametricize a tree & should only be used to coerce    *
*   a phylogeny that fails is.ultrametric due to rounding --  *
*    not as a substitute for formal rate-smoothing methods.   *
***************************************************************
#Add phylum colors next to the tree tips
function_tree <- gheatmap(function_tree, phylum_heatmap, offset=0, width=0.1, colnames=FALSE) +
            scale_fill_manual(values=phylum_colors) +
            labs(fill="Phylum")

#Reset fill scale to use a different colour profile in the heatmap
function_tree <- function_tree + new_scale_fill()

#Add functions heatmap
function_tree <- gheatmap(function_tree, function_table, offset=0.5, width=3.5, colnames=FALSE) +
            vexpand(.08) +
            coord_cartesian(clip = "off") +
            scale_fill_gradient(low = "#f4f4f4", high = "steelblue", na.value="white") +
            labs(fill="GIFT")

#Reset fill scale to use a different colour profile in the heatmap
function_tree <- function_tree + new_scale_fill()

# Add completeness barplots
function_tree <- function_tree +
            geom_fruit(data=genome_metadata,
            geom=geom_bar,
            grid.params=list(axis="x", text.size=2, nbreak = 1),
            axis.params=list(vline=TRUE),
            mapping = aes(x=length, y=genome, fill=completeness),
                 offset = 3.8,
                 orientation="y",
                 stat="identity") +
            scale_fill_gradient(low = "#cf8888", high = "#a2cc87") +
            labs(fill="Genome\ncompleteness")

function_tree

5.3 Functional ordination

# Generate the tSNE ordination
tSNE_function <- Rtsne(X=function_table, dims = 2, check_duplicates = FALSE)

# Plot the ordination
function_ordination <- tSNE_function$Y %>%
                as.data.frame() %>%
                mutate(genome=rownames(function_table)) %>%
                inner_join(genome_metadata, by="genome") %>%
                rename(tSNE1="V1", tSNE2="V2") %>%
                select(genome,phylum,tSNE1,tSNE2, length) %>%
                ggplot(aes(x = tSNE1, y = tSNE2, color = phylum, size=length))+
                            geom_point(shape=16, alpha=0.7) +
                            scale_color_manual(values=phylum_colors) +
                            theme_minimal() +
                labs(color="Phylum", size="Genome size") +
                guides(color = guide_legend(override.aes = list(size = 5))) # enlarge Phylum dots in legend

function_ordination